Font Size: a A A

Research Of Intelligent Optimization Algorithms In Node Location Of Wireless Sensor Networks

Posted on:2020-08-03Degree:MasterType:Thesis
Country:ChinaCandidate:B WuFull Text:PDF
GTID:2428330605950749Subject:Electronics and Communications Engineering
Abstract/Summary:PDF Full Text Request
In recent years,with the development of micro-electromechanical technology,microprocessor technology,wireless communication technology and embedded operating system,wireless sensor networks have also made rapid development.Wireless sensor network technology is considered to be the first of the four technologies affecting human life in the 21st century,and has attracted extensive attention from military departments,academia and industry all over the world.Wireless sensor networks need a lot of technical support.Node localization is one of them.We usually use node localization accuracy as one of the important indicators to measure the performance of wireless sensor networks.Node location technology based on Received Signal Intensity Indicator(RSSI)is widely used because of its convenient use and high accuracy,which makes use of wireless communication chips and does not require additional equipment.However,due to the errors in ranging,many experts and scholars modeled the positioning problem of wireless sensor as an optimization problem to reduce the errors.In this paper,the improved intelligent optimization algorithm is applied to solve the optimization problem of node location in order to reduce the impact of ranging errors on the accuracy of positioning results and improve positioning.Accuracy of position.Intelligent optimization algorithm simulates biological behavior in nature.It is a kind of self-organizing and self-learning algorithm.It is suitable for solving large-scale problems.It has the characteristics of parallelism and self-adaptation.It has been widely used in various disciplines.However,a single intelligent optimization algorithm often has some shortcomings,such as easy to fall into local optimum,slow convergence speed and low convergence accuracy.This paper improves the global and local search ability of intelligent optimization algorithm,so that it can converge faster under the premise of guaranteeing the accuracy of optimization.The main research work of this paper is as follows:(1)A particle swarm optimization(PSO)and differential evolution(DE)method for wireless sensor network node localization is proposed.An improved hybrid particle swarm optimization(HPSO)and differential evolution(DE)algorithm are proposed based on the defect that the basic particle swarm optimization(PSO)algorithm is easy to fall into local minimum.Firstly,adaptive inertia weight updating strategy is introduced into particle swarm optimization(PSO)to balance the ability of local optimization and global exploration.Then,the population evolved by PSO is divided into superior population and inferior population,and inferior population is optimized and mutated by improved DE.The hybrid algorithm combines the advantages of particle swarm optimization and differential evolution,and achieves better performance.Through the verification of standard test function,the convergence speed and accuracy of the proposed algorithm are better than those of PSO and DE.Next,the improved method is applied to wireless sensor network node localization.From the simulation results,it can be seen that the accuracy of the improved method is improved by about 0.5m on average compared with PSO,and it has greater advantages in localization.(2)A location method for wireless sensor network nodes based on differential evolutionary genetic algorithm is proposed.Because of the characteristics of the algorithm itself and the search area,it is difficult for a single population to keep further exploring the current optimal value without neglecting the problems in the undeveloped areas.Based on the basic genetic algorithm,a differential evolution mechanism is proposed to take into account the convergence speed and convergence accuracy of the algorithm.The validation of the standard test function shows that the proposed algorithm can not only converge quickly but also avoid falling into local optimum.It is very effective for solving complex optimization problems with multiple local extremums.Next,the improved method is applied to wireless sensor network node localization.From the simulation results,it can be seen that its accuracy is improved by about 0.7m on average compared with CBA,and the localization accuracy is higher.
Keywords/Search Tags:wireless sensor network, node location, particle swarm optimization, differential evolution, genetic algorithm
PDF Full Text Request
Related items